From 58b6c2de3bd9f8b81c543ba81cd1529c221281ae Mon Sep 17 00:00:00 2001 From: Kiryl Date: Thu, 29 Sep 2022 11:21:29 +0300 Subject: [PATCH] make heading removal only for hs --- src/epub_converter/html_epub_processor.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/src/epub_converter/html_epub_processor.py b/src/epub_converter/html_epub_processor.py index 40640c1..fd29817 100644 --- a/src/epub_converter/html_epub_processor.py +++ b/src/epub_converter/html_epub_processor.py @@ -99,11 +99,13 @@ class HtmlEpubProcessor: return text title_of_chapter: str = title_of_chapter.lower() - title_in_text: List[Tag] = chapter_tag.find_all(lambda tag: title_of_chapter == text_preparing(tag) or \ - (title_of_chapter in text_preparing(tag) and - re.findall(r"^h[1-3]$", tag.name or chapter_tag.name))) + title_in_text: List[Tag] = chapter_tag.find_all(lambda tag: (title_of_chapter in text_preparing(tag) and + len(text_preparing(tag)) != 0 and + re.findall(r"^h[1-5]$", tag.name or chapter_tag.name))) - text_in_title: List[Tag] = chapter_tag.find_all(lambda tag: (text_preparing(tag) in title_of_chapter)) + text_in_title: List[Tag] = chapter_tag.find_all(lambda tag: (text_preparing(tag) in title_of_chapter) and + len(text_preparing(tag)) != 0 and + re.findall(r"^h[1-5]$", tag.name or chapter_tag.name)) if title_in_text: self.html_preprocessor._add_span_to_save_ids_for_links( title_in_text[-1], chapter_tag)